Python爬虫(二)——豆瓣图书决策树构建

　　前文参考： https://www.cnblogs.com/LexMoon/p/douban1.html

Matplotlib绘制决策树代码：

 1 # coding=utf-8
 2 import matplotlib.pyplot as plt
 3 
 4 decisionNode = dict(boxstyle='sawtooth', fc='10')
 5 leafNode = dict(boxstyle='round4',fc='0.8')
 6 arrow_args = dict(arrowstyle='<-')
 7 
 8 
 9 
10 def plotNode(nodeTxt, centerPt, parentPt, nodeType):
11     createPlot.ax1.annotate(nodeTxt, xy=parentPt, xycoords='axes fraction',\
12                              xytext=centerPt,textcoords='axes fraction',\
13                              va='center', ha='center',bbox=nodeType,arrowprops\
14                              =arrow_args)
15 
16 
17 def getNumLeafs(myTree):
18     numLeafs = 0
19     firstStr = list(myTree.keys())[0]
20     secondDict = myTree[firstStr]
21     for key in secondDict:
22         if(type(secondDict[key]).__name__ == 'dict'):
23             numLeafs += getNumLeafs(secondDict[key])
24         else:
25             numLeafs += 1
26     return  numLeafs
27 
28 def getTreeDepth(myTree):
29     maxDepth = 0
30     firstStr = list(myTree.keys())[0]
31     secondDict = myTree[firstStr]
32     for key in secondDict:
33         if(type(secondDict[key]).__name__ == 'dict'):
34             thisDepth = 1+getTreeDepth((secondDict[key]))
35         else:
36             thisDepth = 1
37         if thisDepth > maxDepth: maxDepth = thisDepth
38     return maxDepth
39 
40 def retrieveTree(i):
41     #预先设置树的信息
42     listOfTree = [{'no surfacing':{0:'no',1:{'flipper':{0:'no',1:'yes'}}}},
43         {'no surfacing':{0:'no',1:{'flipper':{0:{'head':{0:'no',1:'yes'}},1:'no'}}}},
44         {'Comment score greater than 8.0':{0:{'Comment score greater than 9.5':{0:'Yes',1:{'More than 45,000 people commented': {
45         0: 'Yes',1: 'No'}}}},1:'No'}}]
46     return listOfTree[i]
47 
48 def createPlot(inTree):
49     fig = plt.figure(1,facecolor='white')
50     fig.clf()
51     axprops = dict(xticks = [], yticks=[])
52     createPlot.ax1 = plt.subplot(111,frameon = False,**axprops)
53     plotTree.totalW = float(getNumLeafs(inTree))
54     plotTree.totalD = float(getTreeDepth(inTree))
55     plotTree.xOff = -0.5/plotTree.totalW;plotTree.yOff = 1.0
56     plotTree(inTree,(0.5,1.0), '')
57     plt.title('Douban reading Decision Tree\n')
58     plt.show()
59 
60 def plotMidText(cntrPt, parentPt,txtString):
61     xMid = (parentPt[0]-cntrPt[0])/2.0 + cntrPt[0]
62     yMid = (parentPt[1] - cntrPt[1])/2.0 + cntrPt[1]
63     createPlot.ax1.text(xMid, yMid, txtString)
64 
65 def plotTree(myTree, parentPt, nodeTxt):
66     numLeafs = getNumLeafs(myTree)
67     depth = getTreeDepth(myTree)
68     firstStr = list(myTree.keys())[0]
69     cntrPt = (plotTree.xOff+(1.0+float(numLeafs))/2.0/plotTree.totalW,\
70               plotTree.yOff)
71     plotMidText(cntrPt,parentPt,nodeTxt)
72     plotNode(firstStr,cntrPt,parentPt,decisionNode)
73     secondDict = myTree[firstStr]
74     plotTree.yOff = plotTree.yOff - 1.0/plotTree.totalD
75     for key in secondDict:
76         if type(secondDict[key]).__name__ == 'dict':
77             plotTree(secondDict[key],cntrPt,str(key))
78         else:
79             plotTree.xOff = plotTree.xOff + 1.0/plotTree.totalW
80             plotNode(secondDict[key],(plotTree.xOff,plotTree.yOff),\
81                      cntrPt,leafNode)
82             plotMidText((plotTree.xOff,plotTree.yOff),cntrPt,str(key))
83     plotTree.yOff = plotTree.yOff + 1.0/plotTree.totalD
84 
85 if __name__ == '__main__':
86     myTree = retrieveTree(2)
87     createPlot(myTree)